光电子技术, 2009, 29 (1): 37, 网络出版: 2010-05-10
基于虹膜图像特征的噪声检测方法
A Noise Detection Method Based on the Characteristics of the Iris Image
摘要
在虹膜识别系统中,采集得到的图像,除了虹膜信息外,一般还会存在睫毛、眼睑及光源的像点等干扰。这会对虹膜的边界定位和特征提取产生影响,并最终导致识别率降低。通过对眼睑、睫毛、光斑噪声检测的研究,根据噪声的特点,提出一种新的快速定位眼睑的方法,并对双阈值检测睫毛的方法进行改进。试验结果表明,该方法能有效去除虹膜区域噪声干扰,提高识别率。
Abstract
In an iris recognition system, the captured iris image contains not only the iris information, but also the eyelids, eyelash, reflection and so on. The disturbed factors will influence iris localization and feature extraction and eventually lead to lower recognition rate. The detection of the eyelids, eyelash, reflecting were studied. According to the characteristics of the eyelids, a new method of detecting the eyelids is proposed in this paper. Extensive experimental result shows that the algorithm has satisfying performance.郑煊|zhengxuan66@163.com
郑煊, 王强德, 刘萌. 基于虹膜图像特征的噪声检测方法[J]. 光电子技术, 2009, 29(1): 37. Zheng Xuan, Wang Qiangde, Liu Meng. A Noise Detection Method Based on the Characteristics of the Iris Image[J]. Optoelectronic Technology, 2009, 29(1): 37.